INDEX

Explanations

instances of the word "talk" in various contexts

oai_token-act-pair · gpt-3.5-turbo

the act of discussing or communicating about various topics

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

emale

-0.82

rehens

-0.73

iverpool

-0.73

ascade

-0.69

eele

-0.68

ettel

-0.67

boa

-0.67

arte

-0.66

zyk

-0.65

iscal

-0.63

POSITIVE LOGITS

 Talk

0.88

 about

0.83

 loudly

0.82

 aloud

0.81

bone

0.80

 talk

0.79

Talk

0.74

 louder

0.74

bag

0.74

 frankly

0.73

Activations Density 0.041%

instances of the word "talk" in various contexts

the act of discussing or communicating about various topics

No Comments

No Known Activations